External pipelines · RISE project catalogue
AutoSurvey
A NeurIPS 2024 framework (arXiv:2406.10252) for automatically generating comprehensive literature surveys from a topic and a paper database. Demonstrated on survey lengths of 8k–64k tokens with reported citation-quality and content-quality scores. Sits squarely in the literature-synthesis stage of the RISE diagram.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by Yidong Wang, Westlake University + Peking University + Nanjing University + HIT Shenzhen + Squirrel AI
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
What it does
Among the first systems to treat *long-form survey writing* (not short-form QA or summarization) as the target task, with explicit evaluation of citation quality at scale. Ships with a 530K-abstract arXiv-CS database used in the published experiments.
- Focus
- literature
- Inputs
- survey-topic
- Outputs
- long-form-survey, citations
- Architecture
- multi-agent, rag-knowledge-base, iterative-loop
- Maintained by
- Yidong Wang; Westlake University + Peking University + Nanjing University + HIT Shenzhen + Squirrel AI
- Started
- 2024
Description
Data model- Discipline
- General
- Method family
- Literature review
- Design
- not specified
- Research stage
- Literature discoveryLiterature synthesisDrafting
- Contributors
- Yidong Wang; Westlake University + Peking University + Nanjing University + HIT Shenzhen + Squirrel AI
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:autosurvey · JSON
Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.
Bring it into the standard
A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.